How to Use the Deepgram MCP in CrewAI

Q: How do I restrict CrewAI agents from deleting Deepgram keys?

You configure a toolfilter in your CrewAI setup to only expose transcribeurl and speaktext to your creative agents. This prevents your analysis crew from ever touching administrative tools like deletekey.

Deploy autonomous agent teams that transcribe, analyze, and synthesize speech using CrewAI and Deepgram.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Deepgram MCP to CrewAI

Create your Vinkius account to connect Deepgram to CrewAI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Deepgram with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assign audio tasks to specialized CrewAI agents

Build a CrewAI team where one agent focuses on transcribing customer calls with Deepgram while another analyzes the text. By equipping your transcription agent with Deepgram's `transcribe_url` tool, CrewAI hands the text over to the analyst agent. This division of labor prevents your CrewAI LLMs from getting overwhelmed with raw Deepgram transcript context. The CrewAI framework passes the Deepgram output between agents using shared memory, ensuring everyone has the context they need to execute their specific roles.

Manage Deepgram accounts autonomously with CrewAI

Let a CrewAI manager agent oversee your Deepgram audio infrastructure by checking balances. Your CrewAI admin agent can call Deepgram's `get_balances` and `send_invite` to add developers dynamically. If a Deepgram API key is compromised, your CrewAI security agent can instantly call `delete_key`. The Deepgram MCP Server gives your CrewAI team the exact administrative access they need.

Run voice-first feedback loops in CrewAI teams

Create CrewAI agents that communicate results using Deepgram speech rather than plain text. Your CrewAI moderator agent can use Deepgram's `speak_text` to generate voice memos summarizing the findings. The Deepgram tools are exposed natively to the CrewAI crew, letting agents decide when voice is appropriate. This underlying Deepgram MCP Server handles the audio encoding for your CrewAI agents.

Setup guide

Set up Deepgram MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Deepgram tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Deepgram Analyst",
    goal="Access and analyze Deepgram data via MCP.",
    backstory="Expert analyst with direct Deepgram access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Deepgram transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Deepgram Analyst",
        goal="Access and analyze Deepgram data via MCP.",
        backstory="Expert analyst with direct Deepgram access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Deepgram transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Deepgram. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Deepgram now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Deepgram MCP in CrewAI

You configure a tool_filter in your CrewAI setup to only expose transcribe_url and speak_text to your creative agents. This prevents your analysis crew from ever touching administrative tools like delete_key.

Yes, the CrewAI framework handles parallel execution, allowing different agents to call transcribe_url and speak_text at the same time. The Deepgram MCP Server handles these concurrent requests through its high-availability Vinkius hosting.

You can assign a dedicated audit agent in CrewAI to periodically run the get_usage tool. This agent can log API consumption metrics and alert the team if the collective audio processing budget is running low.

While you can run it locally, connecting CrewAI to the hosted Vinkius server via HTTP is much simpler. It removes the need to manage local Python subprocesses or node environments for the Deepgram MCP Server transport layer.

All audio streams and generated speech files are processed in zero-trust, ephemeral V8 sandboxes. Vinkius ensures that the Deepgram MCP Server never stores your transcripts or voice outputs, keeping your proprietary audio data strictly private.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript